CoChat
Sign Up
Cited by 1,027AI in cancer detectionCancer Immunotherapy and BiomarkersRadiomics and Machine Learning in Medical Imaging

Spatial organization and molecular correlation of tumor-infiltrating lymphocytes using deep learning on pathology images

Open access
Saltz, Joel, Gupta, Rajarsi, Hou, Le, Kurc, Tahsin, Singh, Pankaj, Nguyen, Vu, Samaras, Dimitris, Shroyer, Kenneth R. +733 more·2018·Cell Reports
DOI 10.1016/j.celrep.2018.03.086PMC PMC5943714
Open this paper in CoChat — free accountOpen PDF

Abstract

Beyond sample curation and basic pathologic characterization, the digitized H&E-stained images of TCGA samples remain underutilized. To highlight this resource, we present mappings of tumor-infiltrating lymphocytes (TILs) based on H&E images from 13 TCGA tumor types. These TIL maps are derived through computational staining using a convolutional neural network trained to classify patches of images. Affinity propagation revealed local spatial structure in TIL patterns and correlation with overall survival. TIL map structural patterns were grouped using standard histopathological parameters. These patterns are enriched in particular T cell subpopulations derived from molecular measures. TIL densities and spatial structure were differentially enriched among tumor types, immune subtypes, and tumor molecular subtypes, implying that spatial infiltrate state could reflect particular tumor cell aberration states. Obtaining spatial lymphocytic patterns linked to the rich genomic characterization of TCGA samples demonstrates one use for the TCGA image archives with insights into the tumor-immune microenvironment.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.celrep.2018.03.086

Cites

62 of 62 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Other efforts have used AI on H&E images to predict TIL presence and PD-L1 expression status in breast cancer.

    “Other efforts have used AI on H&E images to directly predict TIL presence (85,86), a notable prognostic and predictive biomarker in breast cancer, and programmed cell death ligand 1 (PD-L1) expression status, a predictive biomarker for immunotherapies (87).”

    From Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions (2024) · cites this paper as [85]

  • These datasets can be correlated to molecular tumor characteristics and can be used to quantitatively characterize tissue at multiple spatial scales to create biomarkers that predict outcome and treatment response.

    “These datasets can be correlated to molecular tumor characteristics and can be used to quantitatively characterize tissue at multiple spatial scales to create biomarkers that predict outcome and treatment response [150], [152]–[154].”

    From AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020) · cites this paper as [152]

  • These studies showed there are correlations between characterizations of TIL patterns, as analyzed by computerized algorithms, and patient survival rates and groupings of patients based on subclasses of immunotypes.

    “These studies showed there are correlations between characterizations of TIL patterns, as analyzed by computerized algorithms, and patient survival rates and groupings of patients based on subclasses of immunotypes.”

    From AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020) · cites this paper as [152]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. Hou L Singh K Samaras D Kurc TM Gao Y Seidman RJ Saltz JH 2016b Automatic histopathology image analysis with CNNs 2016 New York Scientific Data Summit (NYSDS) IEEE 1 6
  2. Theano Development Team 2016 Theano: A Python framework for fast computation of mathematical expressions Symbolic Computation; Learning; Mathematical Software arXiv:1605.02688v1 · arXiv

Cited by

Sorted by citations

Related

Authors
Saltz, J., Gupta, R., Hou, L., Kurc, T., Singh, P., Nguyen, V., Samaras, D., Shroyer, K. R., Zhao, T., Batiste, R., Van Arnam, J., Caesar-Johnson, S. J., Demchok, J. A., Felau, I., Kasapi, M., Ferguson, M. L., Hutter, C. M., Sofia, H. J., Tarnuzzer, R., Wang, Z., Yang, L., Zenklusen, J. C., Zhang, J. (., Chudamani, S., Liu, J., Lolla, L., Naresh, R., Pihl, T., Sun, Q., Wan, Y., Wu, Y., Cho, J., DeFreitas, T., Frazer, S., Gehlenborg, N., Getz, G., Heiman, D. I., Kim, J., Lawrence, M. S., Lin, P., Meier, S., Noble, M. S., Saksena, G., Voet, D., Zhang, H., Bernard, B., Chambwe, N., Dhankani, V., Knijnenburg, T., Kramer, R., Leinonen, K., Liu, Y., Miller, M., Reynolds, S., Shmulevich, I., Thorsson, V., Zhang, W., Akbani, R., Broom, B. M., Hegde, A. M., Ju, Z., Kanchi, R. S., Korkut, A., Li, J., Liang, H., Ling, S., Liu, W., Lu, Y., Mills, G. B., Ng, K.-S., Rao, A., Ryan, M., Wang, J., Weinstein, J. N., Zhang, J., Abeshouse, A., Armenia, J., Chakravarty, D., Chatila, W. K., de Bruijn, I., Gao, J., Gross, B. E., Heins, Z. J., Kundra, R., La, K., Ladanyi, M., Luna, A., Nissan, M. G., Ochoa, A., Phillips, S. M., Reznik, E., Sanchez-Vega, F., Sander, C., Schultz, N., Sheridan, R., Sumer, S. O., Sun, Y., Taylor, B. S., Wang, J., Zhang, H., Anur, P., Peto, M., Spellman, P., Benz, C., Stuart, J. M., Wong, C. K., Yau, C., Hayes, D. N., Parker, J. S., Wilkerson, M. D., Ally, A., Balasundaram, M., Bowlby, R., Brooks, D., Carlsen, R., Chuah, E., Dhalla, N., Holt, R., Jones, S. J. M., Kasaian, K., Lee, D., Ma, Y., Marra, M. A., Mayo, M., Moore, R. A., Mungall, A. J., Mungall, K., Robertson, A. G., Sadeghi, S., Schein, J. E., Sipahimalani, P., Tam, A., Thiessen, N., Tse, K., Wong, T., Berger, A. C., Beroukhim, R., Cherniack, A. D., Cibulskis, C., Gabriel, S. B., Gao, G. F., Ha, G., Meyerson, M., Schumacher, S. E., Shih, J., Kucherlapati, M. H., Kucherlapati, R. S., Baylin, S., Cope, L., Danilova, L., Bootwalla, M. S., Lai, P. H., Maglinte, D. T., Van Den Berg, D. J., Weisenberger, D. J., Auman, J. T., Balu, S., Bodenheimer, T., Fan, C., Hoadley, K. A., Hoyle, A. P., Jefferys, S. R., Jones, C. D., Meng, S., Mieczkowski, P. A., Mose, L. E., Perou, A. H., Perou, C. M., Roach, J., Shi, Y., Simons, J. V., Skelly, T., Soloway, M. G., Tan, D., Veluvolu, U., Fan, H., Hinoue, T., Laird, P. W., Shen, H., Zhou, W., Bellair, M., Chang, K., Covington, K., Creighton, C. J., Dinh, H., Doddapaneni, H., Donehower, L. A., Drummond, J., Gibbs, R. A., Glenn, R., Hale, W., Han, Y., Hu, J., Korchina, V., Lee, S., Lewis, L., Li, W., Liu, X., Morgan, M., Morton, D., Muzny, D., Santibanez, J., Sheth, M., Shinbrot, E., Wang, L., Wang, M., Wheeler, D. A., Xi, L., Zhao, F., Hess, J., Appelbaum, E. L., Bailey, M., Cordes, M. G., Ding, L., Fronick, C. C., Fulton, L. A., Fulton, R. S., Kandoth, C., Mardis, E. R., McLellan, M. D., Miller, C. A., Schmidt, H. K., Wilson, R. K., Crain, D., Curley, E., Gardner, J., Lau, K., Mallery, D., Morris, S., Paulauskis, J., Penny, R., Shelton, C., Shelton, T., Sherman, M., Thompson, E., Yena, P., Bowen, J., Gastier-Foster, J. M., Gerken, M., Leraas, K. M., Lichtenberg, T. M., Ramirez, N. C., Wise, L., Zmuda, E., Corcoran, N., Costello, T., Hovens, C., Carvalho, A. L., de Carvalho, A. C., Fregnani, J. H., Longatto-Filho, A., Reis, R. M., Scapulatempo-Neto, C., Silveira, H. C. S., Vidal, D. O., Burnette, A., Eschbacher, J., Hermes, B., Noss, A., Singh, R., Anderson, M. L., Castro, P. D., Ittmann, M., Huntsman, D., Kohl, B., Le, X., Thorp, R., Andry, C., Duffy, E. R., Lyadov, V., Paklina, O., Setdikova, G., Shabunin, A., Tavobilov, M., McPherson, C., Warnick, R., Berkowitz, R., Cramer, D., Feltmate, C., Horowitz, N., Kibel, A., Muto, M., Raut, C. P., Malykh, A., Barnholtz-Sloan, J. S., Barrett, W., Devine, K., Fulop, J., Ostrom, Q. T., Shimmel, K., Wolinsky, Y., Sloan, A. E., De Rose, A., Giuliante, F., Goodman, M., Karlan, B. Y., Hagedorn, C. H., Eckman, J., Harr, J., Myers, J., Tucker, K., Zach, L. A., Deyarmin, B., Hu, H., Kvecher, L., Larson, C., Mural, R. J., Somiari, S., Vicha, A., Zelinka, T., Bennett, J., Iacocca, M., Rabeno, B., Swanson, P., Latour, M., Lacombe, L., Têtu, B., Bergeron, A., McGraw, M., Staugaitis, S. M., Chabot, J., Hibshoosh, H., Sepulveda, A., Su, T., Wang, T., Potapova, O., Voronina, O., Desjardins, L., Mariani, O., Roman-Roman, S., Sastre, X., Stern, M.-H., Cheng, F., Signoretti, S., Berchuck, A., Bigner, D., Lipp, E., Marks, J., McCall, S., McLendon, R., Secord, A., Sharp, A., Behera, M., Brat, D. J., Chen, A., Delman, K., Force, S., Khuri, F., Magliocca, K., Maithel, S., Olson, J. J., Owonikoko, T., Pickens, A., Ramalingam, S., Shin, D. M., Sica, G., Van Meir, E. G., Zhang, H., Eijckenboom, W., Gillis, A., Korpershoek, E., Looijenga, L., Oosterhuis, W., Stoop, H., van Kessel, K. E., Zwarthoff, E. C., Calatozzolo, C., Cuppini, L., Cuzzubbo, S., DiMeco, F., Finocchiaro, G., Mattei, L., Perin, A., Pollo, B., Chen, C., Houck, J., Lohavanichbutr, P., Hartmann, A., Stoehr, C., Stoehr, R., Taubert, H., Wach, S., Wullich, B., Kycler, W., Murawa, D., Wiznerowicz, M., Chung, K., Edenfield, W. J., Martin, J., Baudin, E., Bubley, G., Bueno, R., De Rienzo, A., Richards, W. G., Kalkanis, S., Mikkelsen, T., Noushmehr, H., Scarpace, L., Girard, N., Aymerich, M., Campo, E., Giné, E., Guillermo, A. L., Van Bang, N., Hanh, P. T., Phu, B. D., Tang, Y., Colman, H., Evason, K., Dottino, P. R., Martignetti, J. A., Gabra, H., Juhl, H., Akeredolu, T., Stepa, S., Hoon, D., Ahn, K., Kang, K. J., Beuschlein, F., Breggia, A., Birrer, M., Bell, D., Borad, M., Bryce, A. H., Castle, E., Chandan, V., Cheville, J., Copland, J. A., Farnell, M., Flotte, T., Giama, N., Ho, T., Kendrick, M., Kocher, J.-P., Kopp, K., Moser, C., Nagorney, D., O’Brien, D., O’Neill, B. P., Patel, T., Petersen, G., Que, F., Rivera, M., Roberts, L., Smallridge, R., Smyrk, T., Stanton, M., Thompson, R. H., Torbenson, M., Yang, J. D., Zhang, L., Brimo, F., Ajani, J. A., Gonzalez, A. M. A., Behrens, C., Bondaruk, J., Broaddus, R., Czerniak, B., Esmaeli, B., Fujimoto, J., Gershenwald, J., Guo, C., Lazar, A. J., Logothetis, C., Meric-Bernstam, F., Moran, C., Ramondetta, L., Rice, D., Sood, A., Tamboli, P., Thompson, T., Troncoso, P., Tsao, A., Wistuba, I., Carter, C., Haydu, L., Hersey, P., Jakrot, V., Kakavand, H., Kefford, R., Lee, K., Long, G., Mann, G., Quinn, M., Saw, R., Scolyer, R., Shannon, K., Spillane, A., Stretch, O., Synott, M., Thompson, J., Wilmott, J., Al-Ahmadie, H., Chan, T. A., Ghossein, R., Gopalan, A., Levine, D. A., Reuter, V., Singer, S., Singh, B., Tien, N. V., Broudy, T., Mirsaidi, C., Nair, P., Drwiega, P., Miller, J., Smith, J., Zaren, H., Park, J.-W., Hung, N. P., Kebebew, E., Linehan, W. M., Metwalli, A. R., Pacak, K., Pinto, P. A., Schiffman, M., Schmidt, L. S., Vocke, C. D., Wentzensen, N., Worrell, R., Yang, H., Moncrieff, M., Goparaju, C., Melamed, J., Pass, H., Botnariuc, N., Caraman, I., Cernat, M., Chemencedji, I., Clipca, A., Doruc, S., Gorincioi, G., Mura, S., Pirtac, M., Stancul, I., Tcaciuc, D., Albert, M., Alexopoulou, I., Arnaout, A., Bartlett, J., Engel, J., Gilbert, S., Parfitt, J., Sekhon, H., Thomas, G., Rassl, D. M., Rintoul, R. C., Bifulco, C., Tamakawa, R., Urba, W., Hayward, N., Timmers, H., Antenucci, A., Facciolo, F., Grazi, G., Marino, M., Merola, R., de Krijger, R., Gimenez-Roqueplo, A.-P., Piché, A., Chevalier, S., McKercher, G., Birsoy, K., Barnett, G., Brewer, C., Farver, C., Naska, T., Pennell, N. A., Raymond, D., Schilero, C., Smolenski, K., Williams, F., Morrison, C., Borgia, J. A., Liptay, M. J., Pool, M., Seder, C. W., Junker, K., Omberg, L., Dinkin, M., Manikhas, G., Alvaro, D., Bragazzi, M. C., Cardinale, V., Carpino, G., Gaudio, E., Chesla, D., Cottingham, S., Dubina, M., Moiseenko, F., Dhanasekaran, R., Becker, K.-F., Janssen, K.-P., Slotta-Huspenina, J., Abdel-Rahman, M. H., Aziz, D., Bell, S., Cebulla, C. M., Davis, A., Duell, R., Elder, J. B., Hilty, J., Kumar, B., Lang, J., Lehman, N. L., Mandt, R., Nguyen, P., Pilarski, R., Rai, K., Schoenfield, L., Senecal, K., Wakely, P., Hansen, P., Lechan, R., Powers, J., Tischler, A., Grizzle, W. E., Sexton, K. C., Kastl, A., Henderson, J., Porten, S., Waldmann, J., Fassnacht, M., Asa, S. L., Schadendorf, D., Couce, M., Graefen, M., Huland, H., Sauter, G., Schlomm, T., Simon, R., Tennstedt, P., Olabode, O., Nelson, M., Bathe, O., Carroll, P. R., Chan, J. M., Disaia, P., Glenn, P., Kelley, R. K., Landen, C. N., Phillips, J., Prados, M., Simko, J., Smith-McCune, K., VandenBerg, S., Roggin, K., Fehrenbach, A., Kendler, A., Sifri, S., Steele, R., Jimeno, A., Carey, F., Forgie, I., Mannelli, M., Carney, M., Hernandez, B., Campos, B., Herold-Mende, C., Jungk, C., Unterberg, A., von Deimling, A., Bossler, A., Galbraith, J., Jacobus, L., Knudson, M., Knutson, T., Ma, D., Milhem, M., Sigmund, R., Godwin, A. K., Madan, R., Rosenthal, H. G., Adebamowo, C., Adebamowo, S. N., Boussioutas, A., Beer, D., Giordano, T., Mes-Masson, A.-M., Saad, F., Bocklage, T., Landrum, L., Mannel, R., Moore, K., Moxley, K., Postier, R., Walker, J., Zuna, R., Feldman, M., Valdivieso, F., Dhir, R., Luketich, J., Pinero, E. M. M., Quintero-Aguilo, M., Carlotti, C. G., Dos Santos, J. S., Kemp, R., Sankarankuty, A., Tirapelli, D., Catto, J., Agnew, K., Swisher, E., Creaney, J., Robinson, B., Shelley, C. S., Godwin, E. M., Kendall, S., Shipman, C., Bradford, C., Carey, T., Haddad, A., Moyer, J., Peterson, L., Prince, M., Rozek, L., Wolf, G., Bowman, R., Fong, K. M., Yang, I., Korst, R., Rathmell, W. K., Fantacone-Campbell, J. L., Hooke, J. A., Kovatich, A. J., Shriver, C. D., DiPersio, J., Drake, B., Govindan, R., Heath, S., Ley, T., Van Tine, B., Westervelt, P., Rubin, M. A., Lee, J. I., Aredes, N. D., Mariamidze, A., Shmulevich, I., Rao, A. U. K., Lazar, A. J., Sharma, A., & Thorsson, V.
Affiliations
  • Stony Brook Medicine (US)
  • Stony Brook University (US)
  • The University of Texas MD Anderson Cancer Center (US)
  • Emory University (US)
  • Institute for Systems Biology (US)
  • University of Pennsylvania (US)
Corresponding author
Saltz, Joel
ORCID
Venue
Cell Reports
Publisher
Elsevier BV
Published
2018-04
Volume
23
Issue
1
Pages
181-193.e7
ISSN
2211-1247 (ISSN-L)
DOI
10.1016/j.celrep.2018.03.086
PMC
PMC5943714
OpenAlex
W2796409016
Cited by
1,027
References
62
Citations by year
2026: 111 · 2025: 123 · 2024: 117 · 2023: 142 · 2022: 152 · 2021: 161 · 2020: 130 · 2019: 61 · 2018: 29
FWCI
52.91
Type
journal article
Language
en
Open access
Licence
Locations
  • Cell Reports (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • Europe PMC (PubMed Central) (acceptedVersion)
  • PubMed Central (acceptedVersion)
  • IRIS Research product catalog (Sapienza University of Rome) (submittedVersion, other-oa)
  • UWA Profiles and Research Repository (UWA) (submittedVersion, cc-by-nc-nd)
  • Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano) (submittedVersion, other-oa)
  • Bern Open Repository and Information System (University of Bern) (submittedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • eScholarship (California Digital Library) (submittedVersion, cc-by-nc-nd)
  • mediaTUM (Technical University of Munich) (submittedVersion, other-oa)
  • Spiral (Imperial College London) (submittedVersion, cc-by-nc-nd)
  • Open Access CRIS of the University of Bern
Funders
  • American Cancer Society (RSG-16-005-01)
  • Cancer Research Institute
  • National Cancer Institute (U24 CA143867, U54 HG003079, U24 CA143799, U24 CA143840, U24 CA143848, U54 HG003067, 14X138, U24 CA143835, HHSN261201400007C, U24CA215109, U24 CA143883, U24 CA143866, 1U24CA199461-01, U24CA180924, U24CA210950, CPRIT RP150578, U24 CA143845, U24 CA144025, U24 CA143882, U24 CA143843, U24 CA143858, P30 CA016672, U54 HG003273, P30 CA01667)
  • National Science Foundation (1531492, ACI-1548562, TG-ASC130023)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Oncology › Cancer Immunotherapy and Biomarkers
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
Keywords
tumor-infiltrating lymphocytes, tumor immune microenvironment, convolutional neural networks, affinity propagation, T cell subsets, tumor molecular subtypes, immune subtypes, overall survival, tumor-infiltrating immune cells
MeSH terms
Deep Learning, Humans, Image Interpretation, Computer-Assisted, Neoplasms, Lymphocytes, Tumor-Infiltrating

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review