bims-mesote 2021-06-20 papers

Issue of 2021–06–20
five papers selected by
Laura Mannarino, Humanitas Research

Oncotarget. 2021 Jun 08. 12(12): 1187-1196

Deep learning with deep convolutional neural network using FDG-PET/CT for malignant pleural mesothelioma diagnosis.

Kazuhiro Kitajima, Hidetoshi Matsuo, Atsushi Kono, Kozo Kuribayashi, Takashi Kijima, Masaki Hashimoto, Seiki Hasegawa, Takamichi Murakami, Koichiro Yamakado.

OBJECTIVES: This study analyzed an artificial intelligence (AI) deep learning method with a three-dimensional deep convolutional neural network (3D DCNN) in regard to diagnostic accuracy to differentiate malignant pleural mesothelioma (MPM) from benign pleural disease using FDG-PET/CT results.
RESULTS: For protocol A, the area under the ROC curve (AUC)/sensitivity/specificity/accuracy values were 0.825/77.9% (81/104)/76.4% (55/72)/77.3% (136/176), while those for protocol B were 0.854/80.8% (84/104)/77.8% (56/72)/79.5% (140/176), for protocol C were 0.881/85.6% (89/104)/75.0% (54/72)/81.3% (143/176), and for protocol D were 0.896/88.5% (92/104)/73.6% (53/72)/82.4% (145/176). Protocol D showed significantly better diagnostic performance as compared to A, B, and C in ROC analysis (p = 0.031, p = 0.0020, p = 0.041, respectively).
MATERIALS AND METHODS: Eight hundred seventy-five consecutive patients with histologically proven or suspected MPM, shown by history, physical examination findings, and chest CT results, who underwent FDG-PET/CT examinations between 2007 and 2017 were investigated in a retrospective manner. There were 525 patients (314 MPM, 211 benign pleural disease) in the deep learning training set, 174 (102 MPM, 72 benign pleural disease) in the validation set, and 176 (104 MPM, 72 benign pleural disease) in the test set. Using AI with PET/CT alone (protocol A), human visual reading (protocol B), a quantitative method that incorporated maximum standardized uptake value (SUVmax) (protocol C), and a combination of PET/CT, SUVmax, gender, and age (protocol D), obtained data were subjected to ROC curve analyses.
CONCLUSIONS: Deep learning with 3D DCNN in combination with FDG-PET/CT imaging results as well as clinical features comprise a novel potential tool shows flexibility for differential diagnosis of MPM.

Keywords: FDG (fluorodeoxyglucose); PET-CT (positron emission tomography-computed tomography); artificial intelligence; deep learning; mesothelioma

DOI: https://doi.org/10.18632/oncotarget.27979

Chest. 2021 Jun 10. pii: S0012-3692(21)01104-1. [Epub ahead of print]

The association between pleural fluid exposure and survival in pleural mesothelioma.

Rachelle Asciak, Nikolaos I Kanellakis, Anna Bibby, Andrew Kidd, Stephen Gerry, Rachel Mercer, Nick Maskell, Kevin G Blyth, Peter Fsadni, Stephen Montefort, Ioannis Psallidas, Najib M Rahman.

BACKGROUND: Most patients with malignant pleural mesothelioma (MPM) present with malignant pleural effusion (MPE). There is in vitro evidence that MPE may not be a simple bystander of malignancy, but potentially has biological properties improving cancer cell survival and promoting cancer progression. If this is the case, MPE management may need to shift from current symptomatic strategies to aggressive fluid removal to impact on survival.
RESEARCH QUESTION: Is there an association between pleural fluid exposure and survival in MPM?
STUDY DESIGN AND METHODS: Data on 761 patients diagnosed with MPM between 2008-2018 were collected from patient medical records in 3 UK pleural units. Data included factors previously identified as influencing prognosis in MPM. Medical imaging was reviewed for presence, size and duration of pleural effusion. Time-dependent covariate analysis of pleural fluid exposure and survival (model included weight loss, serum albumin, Hb, MPM subtype, performance status, chemotherapy, age), and multivariable cox regression analysis of pleurodesis and survival were conducted.
RESULTS: Median overall survival was 278 days (IQR 127-505, 95% CI 253-301). Pleural fluid exposure duration showed no association with survival (HR 1.0, 95% CI 1.0-1.0). Median survival was 473, 378 and 258 days with complete, partial, and no pleurodesis (p 0.008).
INTERPRETATION: Pleurodesis success appears to be associated with improved survival, however it is unclear whether duration of MPM exposure to pleural fluid is associated with survival within the limitations of this retrospective study. Future prospective studies are required to assess this potentially important mechanism.

DOI: https://doi.org/10.1016/j.chest.2021.05.063

Sci Rep. 2021 Jun 15. 11(1): 12554

CLDN15 is a novel diagnostic marker for malignant pleural mesothelioma.

Masayuki Watanabe, Tomohito Higashi, Kana Ozeki, Atsuko Y Higashi, Kotaro Sugimoto, Hayato Mine, Hironori Takagi, Yuki Ozaki, Satoshi Muto, Naoyuki Okabe, Yuki Matsumura, Takeo Hasegawa, Yutaka Shio, Hiroyuki Suzuki, Hideki Chiba.

Malignant mesothelioma is a cancer with a poor survival rate. It is difficult to diagnose mesotheliomas because they show a variety of histological patterns similar to those of various other cancers. However, since currently used positive markers for mesotheliomas may show false positives or false negatives, a novel mesothelial positive marker is required. In the present study, we screened 25 claudins and found that claudin-15 is expressed in the mesothelial cells. We made new rat anti-human claudin-15 (CLDN15) monoclonal antibodies that selectively recognize CLDN15, and investigated whether CLDN15 is a good positive marker for malignant pleural mesotheliomas (MPMs) using MPM tissue samples by immunohistochemistry and semi-quantification of the expression level using an immunoreactive score (IRS) method. Of 42 MPM samples, 83% were positive for CLDN15. The positive ratio was equal to or greater than other positive markers for MPMs including calretinin (81%), WT-1 (50%), and D2-40 (81%). In 50 lung adenocarcinoma sections, four cases were positive for CLDN15 and the specificity (92%) was comparable with other markers (90-100%). Notably, CLDN15 was rarely detected in 24 non-mesothelial tumors in the tissue microarray (12/327 cases). In conclusion, CLDN15 can be used in the clinical setting as a positive marker for MPM diagnosis.

DOI: https://doi.org/10.1038/s41598-021-91464-0

BMJ Case Rep. 2021 Jun 15. pii: e242510. [Epub ahead of print]14(6):

Pleural malignant mesothelioma with metastatic deposition in the tongue.

Matthew Steward, Catharine Pearce, Manish Powari, Hugh Bakere.

A 70-year-old man with epithelioid malignant pleural mesothelioma was referred to the maxillofacial surgery department with a painful lesion on the lateral border of his tongue which interfered with swallowing. Physical examination demonstrated a 3 cm firm, non-ulcerated mass on the left lateral tongue, histologically shown to be metastatic epithelioid mesothelioma. MRI of the neck and CT scan of the thorax, abdomen and pelvis scans also demonstrated progressive local and metastatic disease. The patient was not felt to be fit for further treatment. More than 90% of oral cavity cancers are squamous cell carcinoma. All reported cases of metastasis of malignant mesothelioma to the tongue have been of the epithelioid subtype with 10 cases reported in the literature to date. Diagnosis is important as tongue lesions can significantly impact on quality of life and synchronous tongue primaries should be ruled out. Tongue lesions may herald metastases to other extrapleural locations.

Keywords: cancer intervention; respiratory cancer

DOI: https://doi.org/10.1136/bcr-2021-242510