組織切片識(shí)別可預(yù)測(cè)結(jié)直腸癌預(yù)后
近日，挪威奧斯陸大學(xué)醫(yī)院H?vard E Danielsen研究團(tuán)隊(duì)研究了預(yù)測(cè)結(jié)直腸癌結(jié)局的深度學(xué)習(xí)。該研究于2020年2月1日發(fā)表于國際優(yōu)異學(xué)術(shù)期刊《柳葉刀》雜志上。
為了完善輔助治療的選擇，早期結(jié)直腸癌患者分層的預(yù)后標(biāo)記物急需改善。該研究的目的是通過使用深度學(xué)習(xí)直接分析掃描的常規(guī)蘇木精和伊紅染色切片，從而開發(fā)一種生物標(biāo)記物，來預(yù)測(cè)大腸癌切除術(shù)后患者的預(yù)后。
研究組從四個(gè)隊(duì)列中疾病預(yù)后明顯較好或較差的患者中提取超過1200萬個(gè)圖像塊，用于訓(xùn)練10個(gè)卷積神經(jīng)網(wǎng)絡(luò)，以構(gòu)建分類超大型異構(gòu)圖像。
結(jié)合10個(gè)網(wǎng)絡(luò)的預(yù)后生物標(biāo)記物通過非明顯預(yù)后的患者來確定。該標(biāo)記物在920名患者身上進(jìn)行了測(cè)試，載玻片在英國制備，然后根據(jù)預(yù)先確定的方案在1122名患者身上進(jìn)行獨(dú)立驗(yàn)證，這些患者使用單藥卡培他濱進(jìn)行治療，載玻片在挪威制備。所有隊(duì)列只包括可切除腫瘤的患者。
來自四個(gè)隊(duì)列的828名患者有明確的腫瘤特異性生存率，將其作為訓(xùn)練隊(duì)列。1645名患者生存率不明顯，用于校正。在驗(yàn)證隊(duì)列的初步分析中，生物標(biāo)記物不良預(yù)后與良好預(yù)后的風(fēng)險(xiǎn)比為3.84，在校正了相同隊(duì)列單變量分析中已建立的預(yù)后標(biāo)記物，例如pN期、pT期、淋巴侵犯、靜脈血管侵犯之后，該風(fēng)險(xiǎn)比為3.04。
總之，結(jié)合蘇木精和伊紅染色腫瘤組織切片的數(shù)字掃描，開發(fā)了一種臨床可用的預(yù)后標(biāo)記物。在大量獨(dú)立的患者群體中，該檢測(cè)已廣泛評(píng)估，與已建立的分子和形態(tài)學(xué)預(yù)后標(biāo)記物相互依賴，并優(yōu)于后者，且在腫瘤期和淋巴結(jié)期結(jié)果一致。
生物標(biāo)記物將II期和III期患者進(jìn)行足夠明顯的預(yù)后分層，這可用于指導(dǎo)輔助治療的選擇，避免對(duì)極低風(fēng)險(xiǎn)患者進(jìn)行治療，并確定患者受益于更密集的治療方案。
附：英文原文
Title: Deep learning for prediction of colorectal cancer outcome: a discovery and validation study
Author: Ole-Johan Skrede, Sepp De Raedt, Andreas Kleppe, Tarjei S Hveem, Knut Liestl, John Maddison, Hanne A Askautrud, Manohar Pradhan, John Arne Nesheim, Fritz Albregtsen, Inger Nina Farstad, Enric Domingo, David N Church, Arild Nesbakken, Neil A Shepherd, Ian Tomlinson, Rachel Kerr, Marco Novelli, David J Kerr, Hvard E Danielsen
Issue&Volume: 2020/02/01
Abstract:
Background
Improved markers of prognosis are needed to stratify patients with early-stage colorectal cancer to refine selection of adjuvant therapy. The aim of the present study was to develop a biomarker of patient outcome after primary colorectal cancer resection by directly analysing scanned conventional haematoxylin and eosin stained sections using deep learning.
Methods
More than 12?000?000 image tiles from patients with a distinctly good or poor disease outcome from four cohorts were used to train a total of ten convolutional neural networks, purpose-built for classifying supersized heterogeneous images. A prognostic biomarker integrating the ten networks was determined using patients with a non-distinct outcome. The marker was tested on 920 patients with slides prepared in the UK, and then independently validated according to a predefined protocol in 1122 patients treated with single-agent capecitabine using slides prepared in Norway. All cohorts included only patients with resectable tumours, and a formalin-fixed, paraffin-embedded tumour tissue block available for analysis. The primary outcome was cancer-specific survival.
Findings
828 patients from four cohorts had a distinct outcome and were used as a training cohort to obtain clear ground truth. 1645 patients had a non-distinct outcome and were used for tuning. The biomarker provided a hazard ratio for poor versus good prognosis of 3·84 (95% CI 2·72–5·43; p<0·0001) in the primary analysis of the validation cohort, and 3·04 (2·07–4·47; p<0·0001) after adjusting for established prognostic markers significant in univariable analyses of the same cohort, which were pN stage, pT stage, lymphatic invasion, and venous vascular invasion.
Interpretation
A clinically useful prognostic marker was developed using deep learning allied to digital scanning of conventional haematoxylin and eosin stained tumour tissue sections. The assay has been extensively evaluated in large, independent patient populations, correlates with and outperforms established molecular and morphological prognostic markers, and gives consistent results across tumour and nodal stage. The biomarker stratified stage II and III patients into sufficiently distinct prognostic groups that potentially could be used to guide selection of adjuvant treatment by avoiding therapy in very low risk groups and identifying patients who would benefit from more intensive treatment regimes.
DOI: 10.1016/S0140-6736(19)32998-8
Source: https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(19)32998-8/fulltext
聲明：本文版權(quán)歸原作者所有，轉(zhuǎn)載文章僅為傳播更多信息，如作者信息標(biāo)記有誤，或侵犯您的版權(quán)，請(qǐng)聯(lián)系我們，我們將在及時(shí)修改或刪除內(nèi)容，聯(lián)系郵箱：marketing@360worldcare.com
