Prognostic value of deep learning-derived body composition in advanced pancreatic cancer-a retrospective multicenter study.

BACKGROUND: Despite the prognostic relevance of cachexia in pancreatic cancer, individual body composition has not been routinely integrated into treatment planning. In this multicenter study, we investigated the prognostic value of sarcopenia and myosteatosis automatically extracted from routine computed tomography (CT) scans of patients with advanced pancreatic ductal adenocarcinoma (PDAC). PATIENTS AND METHODS: We retrospectively analyzed clinical imaging data of 601 patients from three German cancer centers. We applied a deep learning approach to assess sarcopenia by the abdominal muscle-to-bone ratio (MBR) and myosteatosis by the ratio of abdominal inter- and intramuscular fat to muscle volume. In the pooled cohort, univariable and multivariable analyses were carried out to analyze the association between body composition markers and overall survival (OS). We analyzed the relationship between body composition markers and laboratory values during the first year of therapy in a subgroup using linear regression analysis adjusted for age, sex, and American Joint Committee on Cancer (AJCC) stage. RESULTS: Deep learning-derived MBR [hazard ratio (HR) 0.60, 95% confidence interval (CI) 0.47-0.77, P < 0.005] and myosteatosis (HR 3.73, 95% CI 1.66-8.39, P < 0.005) were significantly associated with OS in univariable analysis. In multivariable analysis, MBR (P = 0.019) and myosteatosis (P = 0.02) were associated with OS independent of age, sex, and AJCC stage. In a subgroup, MBR and myosteatosis were associated with albumin and C-reactive protein levels after initiation of therapy. Additionally, MBR was also associated with hemoglobin and total protein levels. CONCLUSIONS: Our work demonstrates that deep learning can be applied across cancer centers to automatically assess sarcopenia and myosteatosis from routine CT scans. We highlight the prognostic role of our proposed markers and show a strong relationship with protein levels, inflammation, and anemia. In clinical practice, automated body composition analysis holds the potential to further personalize cancer treatment.

Diagnosis of intrauterine fetal growth retardation by DHAS half-life.

A DHAS test (50 mg i.v.) was performed on 49 women with clinically suspected intrauterine fetal growth retardation (IUGR) in the last trimester of pregnancy. A correlation could be established between the serum DHAS halflife (DHAS-T 1/2) of the mother after DHAS loading and the birthweight percentile of the newborns, which were retrospectively divided into two groups; one with regular intrauterine fetal growth (birthweight greater than 10th percentile) (n = 28) and one with poor intrauterine fetal growth (IUGR) (less than 10th percentile) (n = 21). The DHAS loading test was retrospectively evaluated by the correct diagnosis of intrauterine fetal growth; a DHAS halflife below 4.7 h was taken as a threshold for normal intrauterine fetal growth as indicated by a previous study by our group: DHAS-T 1/2 (less than 10th birthweight percentile): 6.00 +/- 1.43 h (mean +/- S.D.) (n = 18), DHAS-T 1/2 (greater than 10th birthweight percentile): 4.37 +/- 1.06 h (mean +/- S.D.) (n = 28). In 89% (16/18) of the cases (less than 10th birthweight percentile), a prolonged DHAS-T 1/2 (greater than 4.7 h) led to the correct diagnosis of an IUGR. In 75% (21/28) of the cases with regular fetal growth, a DHAS-T 1/2 of less than 4.7 h could be registered. In three cases with intrauterine death of the fetus, a prolonged DHAS-T 1/2 of 7.64 +/- 0.37 h (mean +/- S.D.) was found. Furthermore, IUGR could not be detected in three cases by DHAS loading (DHAS-T 1/2 3.77 +/- 0.51 h (mean +/- S.D.) due to betamethasone induction of lung maturation prior to the DHAS test. Indications for the DHAS test include the diagnosis of an ultrasonographically symmetric IUGR (biparietal and thoracic diameters) in cases with an indefinite gestational age and the detection of a placental sulfatase deficiency by means of a delayed conversion of DHAS to dehydroepiandrosterone.

Sulfatase deficiency in the human placenta: clinical findings.

Sulfatase and aromatase are the key enzymes of estrogen biosynthesis in the human placenta. A total of 76 pregnancies with sulfatase deficiency have been reported. Reduced sulfatase activity occurs in 1:2000 of 1:6000 pregnancies. It can be suspected in patients with low urinary excretion or low serum estriol levels. The sulfatase deficiency can be detected during pregnancy by a prolongation of the half-life of dehydroepiandrosterone sulfate (DHAS) after venous DHAS loading (50 or 100 mg). Post partum the placental sulfatase deficiency can be demonstrated in vitro by nonconversion of radioactive DHAS to DHA. Only 7 of the 76 pregnancies described ended with an uncomplicated vaginal delivery after spontaneous onset of labor. A cesarian section was required in 18 cases. The other case reports mostly concern patients associated with a prolonged pregnancy, lack of cervical dilatation, or absent induction of labor. All 76 newborns were male. Sulfatase deficiency is probably a congenital, sex-specific, X-linked placental enzyme defect. A special therapy is not necessary but the antepartum diagnosis is important because this benign disorder has to be discriminated from the more serious fetal adrenal hypoplasia.

Diagnosis of intrauterine fetal growth retardation (IUGR) and placental insufficiency by a dehydroepiandrosterone sulfate (DHAS) loading test.

Chronic placental insufficiency results in intrauterine fetal growth retardation (IUGR). The IUGR can be diagnosed by clinical signs (follow-up of maternal weight, fundus height, abdominal circumference), ultrasound examination (biparietal and thoracic diameters, circumferences of the head and the trunk), and by endocrinologic tests (estrogen determination in serum and urine without and after performance of a DHAS loading test). The different ways of performing the DHAS loading test reported in the literature are reviewed. The DHAS loading test measures the aromatization capacity of the human placenta and indirectly its metabolic exchange capacities. After DHAS loading, estrogens (estrone, estradiol, estriol), DHAS and DHA can be determined in blood and urine; furthermore, changes in urine total estrogen excretion can be evaluated. In conclusion, the best parameter for diagnosing IUGR seems to be the determination of the DHAS half-life after DHAS loading. A prolongation of DHAS half-life (greater than 4.7 h) after DHAS loading (50 mg i.v.) is a good index of IUGR.