Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Bulten, Wouter; Kartasalo, Kimmo; Chen, Po-Hsuan Cameron; Ström, Peter; Pinckaers, Hans; Nagpal, Kunal; Cai, Yuannan; Steiner, David F.; Boven, Hester van; Vink, Robert; Kaa, Christina Hulsbergen–van de; Laak, Jeroen van der; Amin, Mahul B.; Evans, Andrew; Kwast, Theodorus H. van der; Allan, Robert W.; Humphrey, Peter A.; Grönberg, Henrik; Samaratunga, Hemamali; Delahunt, Brett; Tsuzuki, Toyonori; Häkkinen, Tomi; Egevad, Lars; Demkin, Maggie; Dane, Sohier; Tan, Fraser Elisabeth; Valkonen, Masi; Corrado, Greg S.; Peng, Lily; Mermel, Craig H.; Ruusuvuori, Pekka; Litjens, Geert; Eklund, Martin; Brilhante, Américo; Çakır, Aslı; Farré, Xavier; Geronatsiou, Katerina; Molinié, Vincent; Pereira, Guilherme Martins; Roy, Paromita; Saile, Günter; Salles, Paulo G. O.; Schaafsma, Ewout; Tschui, Joëlle; Billoch-Lima, Jorge; Pereira, Emíio M.; Zhou, Ming; He, Shujun; Song, Sejun; Sun, Qian; Yoshihara, Hiroshi; Yamaguchi, Toshiaki; Ono, Kosaku; Shen, Tao; Ji, Jianyi; Roussel, Arnaud; Zhou, Kai-rong; Chai, Tianrui; Weng, Nina; Grechka, Dmitry A.; Shugaev, Maxim V.; Kiminya, Raphael; Kovalev, Vassili; Voynov, Dmitry; Malyshev, Valery; Lapo, Elizabeth; Campos, Manuel; Ota, Noriaki; Yamaoka, Shinsuke; Fujimoto, Yusuke; Yoshioka, Kentaro; Juvonen, Joni; Tukiainen, Mikko; Karlsson, Antti; Guo, Rui; Hsieh, Chia-Lun; Zubarev, Igor; Bukhar, Habib S. T.; Li, Wenyuan; Li, Jiayun; Speier, William; Arnold, Corey; Kim, Kyungdoc; Bae, Byeonguk; Kim, Yeong Won; Lee, Hong-Seok; Park, Jeonghyuk

doi:10.1038/s41591-021-01620-2

Cited by 175 publications

(72 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manual reading of core needle biopsy slides by pathologists is the gold standard in the prostate cancer diagnosis in the clinic. However, it requires the analysis of around 12 (6)(7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18) biopsy cores, including hundreds of glands. Especially for low-grade and low-volume prostate cancer (GS 3+3 and 3+4), identifying the few malignant glands among vastly benign glands is a tedious and challenging task.…”

Section: Discussionmentioning

confidence: 99%

“…Nevertheless, it is easier for an expert pathologist to diagnose high-grade cancers such as GG4 or GG5. On the other hand, it becomes a real challenge to discriminate rare malignant glands among numerous benign glands in low-grade cancers such as GG1 and GG2 [15]. Besides, undetected malignant glands may result in repeat biopsies and missed therapeutic opportunities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An AI-assisted Tool For Efficient Prostate Cancer Diagnosis

Öner

Giron

et al. 2022

Preprint

View full text Add to dashboard Cite

Pathologists diagnose prostate cancer by core needle biopsy. For low-grade and low-volume cases, the pathologists look for the few malignant glands out of hundreds within a core. They may miss the few malignant glands, resulting in repeat biopsies or missed therapeutic opportunities. This study developed a multi-resolution deep learning pipeline detecting malignant glands in core needle biopsies to help pathologists effectively and accurately diagnose prostate cancer in low-grade and low-volume cases. The pipeline consisted of two stages: the gland segmentation model detected the glands within the sections and the multi-resolution model classified each detected gland into benign vs. malignant. Analyzing a gland at multiple resolutions provided the classification model to exploit both morphology information (of nuclei and glands) and neighborhood information (for architectural patterns), important in prostate gland classification. We developed and tested our pipeline on the slides of a local cohort of 99 patients in Singapore. The images were made publicly available, becoming the first digital histopathology dataset of prostatic carcinoma patients of Asian ancestry. Our pipeline successfully classified the core needle biopsy parts (81 parts: 50 benign and 31 malignant) into benign vs. malignant. It achieved an AUROC value of 0.997 (95% CI: 0.987 - 1.000). Moreover, it produced heatmaps highlighting the malignancy of each gland in core needle biopsies. Hence, our pipeline can effectively assist pathologists in core needle biopsy analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An AI-assisted Tool For Efficient Prostate Cancer Diagnosis

Öner

Giron

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…While doing so, we managed to solve some of the shortcomings we encountered previously. Together with the Karolinska Institute and Google Health, we organized the PANDA (Prostate cANcer graDe Assessment) challenge for prostate cancer grading, using biopsy data from over 6000 patients [ 8 ]. Participants had to predict a consensus grade (established by a panel of experienced pathologists) based on only a biopsy WSI, without any detailed pixel-level annotations.…”

Section: Main Textmentioning

confidence: 99%

A Decade of GigaScience: The Challenges of Gigapixel Pathology Images

2022

Self Cite

View full text Add to dashboard Cite

In the last decade, the field of computational pathology has advanced at a rapid pace because of the availability of deep neural networks, which achieved their first successes in computer vision tasks in 2012. An important driver for the progress of the field were public competitions, so called ‘Grand Challenges’, in which increasingly large data sets were offered to the public to solve clinically relevant tasks. Going from the first Pathology challenges, which had data obtained from 23 patients, to current challenges sharing data of thousands of patients, performance of developed deep learning solutions has reached (and sometimes surpassed) the level of experienced pathologists for specific tasks. We expect future challenges to broaden the horizon, for instance by combining data from radiology, pathology and tumor genetics, and to extract prognostic and predictive information independent of currently used grading schemes.

show abstract

“…In recent years, an increasing number of weakly supervised deep learning methods for whole-slide image (WSI) classification has been proposed for various histopathology problems (8)(9)(10)(11)(12)(13). An attractive feature of weakly supervised methods is their ability to enable automatic classification without the need for detailed pixel or regional annotations process.…”

Section: Introductionmentioning

confidence: 99%

AI based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images

Bilal

Tsang

Ali

et al. 2022

Preprint

View full text Add to dashboard Cite

Histopathological examination is a pivotal step in the diagnosis and treatment planning of many major diseases. To facilitate the diagnostic decision-making and reduce the workload of pathologists, we present an AI-based pre-screening tool capable of identifying normal and neoplastic colon biopsies. To learn the differential histological patterns from whole slides images (WSIs) stained with hematoxylin and eosin (H&E), our proposed weakly supervised deep learning method requires only slide-level labels and no detailed cell or region-level annotations. The proposed method was developed and validated on an internal cohort of biopsy slides (n=4 292) from two hospitals labeled with corresponding diagnostic categories assigned by pathologists after reviewing case reports. Performance of the proposed colon cancer pre-screening tool was evaluated in a cross-validation setting using the internal cohort (n=4 292) and also by an external validation on The Cancer Genome Atlas (TCGA) cohort (n=731). With overall cross-validated classification accuracy (AUROC = 0.9895) and external validation accuracy (AUROC = 0.9746), the proposed tool promises high accuracy to assist with the pre-screening of colorectal biopsies in clinical practice. Analysis of saliency maps confirms the representation of disease heterogeneity in model predictions and their association with relevant pathological features. The proposed AI tool correctly reported some slides as neoplastic while clinical reports suggested they were normal. Additionally, we analyzed genetic mutations and gene enrichment analysis of AI-generated neoplastic scores to gain further insight into the model predictions and explore the association between neoplastic histology and genetic heterogeneity through representative genes and signaling pathways.

show abstract

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Cited by 175 publications

References 38 publications

An AI-assisted Tool For Efficient Prostate Cancer Diagnosis

An AI-assisted Tool For Efficient Prostate Cancer Diagnosis

A Decade of GigaScience: The Challenges of Gigapixel Pathology Images

AI based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images

Contact Info

Product

Resources

About