A method for labelling lesions for machine learning and some new observations on osteochondrosis in computed tomographic scans of four pig joints

Background

Osteochondrosis is a major cause of leg weakness in pigs. Selection against osteochondrosis is currently based on manual scoring of computed tomographic (CT) scans for the presence of osteochondrosis manifesta lesions. It would be advantageous if osteochondrosis could be diagnosed automatically, through artificial intelligence methods using machine learning. The aim of this study was to describe a method for labelling articular osteochondrosis lesions in CT scans of four pig joints to guide development of future machine learning algorithms, and to report new observations made during the labelling process. The shoulder, elbow, stifle and hock joints were evaluated in CT scans of 201 pigs.

Results

Six thousand two hundred fifty osteochondrosis manifesta and cyst-like lesions were labelled in 201 pigs representing a total volume of 211,721.83 mm³. The per-joint prevalence of osteochondrosis ranged from 64.7% in the hock to 100% in the stifle joint. The lowest number of lesions was found in the hock joint at 208 lesions, and the highest number of lesions was found in the stifle joint at 4306 lesions. The mean volume per lesion ranged from 26.21 mm³ in the shoulder to 42.06 mm³ in the elbow joint. Pigs with the highest number of lesions had small lesions, whereas pigs with few lesions frequently had large lesions, that have the potential to become clinically significant. In the stifle joint, lesion number had a moderate negative correlation with mean lesion volume at r = − 0.54, p < 0.001.

Conclusions

The described labelling method is an important step towards developing a machine learning algorithm that will enable automated diagnosis of osteochondrosis manifesta and cyst-like lesions. Both lesion number and volume should be considered during breeding selection. The apparent inverse relationship between lesion number and volume warrants further investigation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12917-022-03426-x.

Biomechanical loading of the porcine femorotibial joint during maximal movements: An exploratory, ex vivo study

Thus far, there is a lack of scientific investigation regarding the hypothesis that biomechanical factors contribute to the cross-species pathogenesis of osteochondrosis (OC). Therefore, the aim of this pilot study was to investigate whether high (peak) pressures occur in the porcine femorotibial (FT) joint. In this experimental, ex vivo study, the right hind limbs of seven weaned piglets were subjected to maximal joint excursions, as a priori radiologically estimated. Subsequently, the intra-articular pressures were measured using sensors placed in both the medial and the lateral compartments of the FT joint. The overall highest individual peak pressure was found in the lateral FT joint during maximal extension (2611 kPa; group mean ± standard deviation (SD) 982.3 ± 988.2 kPa). In the medial FT joint, the highest individual peak pressure was found during maximal adduction (1481 kPa; group mean ± SD 664.9 ± 393.2 kPa). Moreover, nearly 30% of the ex vivo peak pressures were above published thresholds for cartilage catabolism (>500 kPa/0.5 MPa), but not for interfering with cell viability (>5 MPa). In conclusion, this ex vivo study on FT joint pressures in weaned piglets showed that FT joint movements at maximal excursions are related to concomitant internal peak joint pressures. More studies should be performed to evaluate the possible biomechanical relation of these observations with osteochondrosis, which would allow the design of preventive measures in the pig industry, to avoid extreme limb movements and concomitant joint peak pressures in vivo.

Effects of supplementing organic microminerals and methionine with or without limiting growth during the rearing phase of replacement gilts on lameness, growth, and body composition

Previous research suggested that lameness in growing pigs could be reduced using feeding strategies, such as limiting growth rate and supplementing trace minerals (TM) and (or) methionine (Met). The present study evaluates effects of 1) TM and Met and 2) limiting total lysine (Lys) during the rearing phase (90 d) of gilts (as a means to limit growth rate) on lameness, performance, and sow claw health and productivity (to first parity). Gilts (n = 240; 58.0 ± 11.1 kg body weight [BW]) were blocked, distributed into pens of 10 gilts, and pens were allocated to a 2 × 2 factorial arrangement. Factors were: 1) control or TM plus Met, which provided additional 10, 20, and 50 mg/kg of chelated copper, manganese, and zinc, respectively (0.1%, Aplomotec Plus, Tecnología & Vitaminas, S.L.; Alforja, Spain), and a 1.01 Met:Lys ratio and 2) standard Lys was formulated to meet growth requirements or low Lys to 19% below growth requirements. Feeding was provided through two phases, first between 119 and 163 d of age (phase I) and the second between 163 and 209 d of age (phase II). Diets had 2.43 and 2.31 Mcal net energy/kg for phases I and II, respectively, and were offered ad libitum. Low Lys did not affect feed intake but rather reduced average daily gain (ADG) by 6.35% and the final BW by 3.80% compared with standard Lys (P < 0.001). Low Lys reduced ADG (P < 0.001) and gain:feed (P = 0.012) during phase I but not during phase II. Lameness prevalence was 7.92% during rearing and increased with time (P < 0.001). Final BW (151 kg) and ADG (989 g) were similar (P > 0.05) whether gilts displayed lameness or not. Lameness was low in severity and not affected by dietary factors. However, TM- plus Met-fed gilts were 19.2 kg heavier (P = 0.016) than were control at lameness detection. On the sow farm, there was no evidence for differences in lameness or claw lesions among previous dietary treatments. In conclusion, lameness prevalence during the rearing phase was similar, independent of TM plus Met supplement, low Lys, or the interaction. Insufficient reduction of ADG and low severity in lameness may have limited the potential of dietary treatments. Moreover, a greater deficiency of Lys would be needed to achieve the degree of growth reduction previously reported to lessen lameness through feed restriction.

Effects of supplementing organic microminerals and methionine during the rearing phase of replacement gilts on lameness, growth, and body composition

Lameness is a primary reason for culling and mortality within a sow herd. This study evaluated the impact of feeding organic trace minerals and methionine (Met) to growing gilts (134 d) on lameness, performance, body composition and claw health (to first parity), productivity (to second parity), and reproductive performance through 2 parities. Young gilts (28.8 ± 8.8 kg of body weight [BW], n = 360) were BW blocked (10 gilts/pen) and randomly allotted to 1 of 4 dietary treatments: control (CON, basal diet); CON plus organic minerals (MIN, at 10, 20, and 50 mg/kg of Cu, Mn, and Zn, respectively; Aplomotec Plus, Tecnología & Vitaminas, S.L, Alforja, Spain); additional Met (MET, at 102% Met: Lys); and MET plus MIN (MM). Feed was provided ad libitum. Lameness, BW, and body composition were measured 7 times during rearing, at gilt service, day 109 of gestation, and first weaning. Gilts fed the MM diet had lower average daily feed intake (5.1%) and final BW (2.1%) than CON gilts (P < 0.05), whereas MIN and MET were intermediate and not different from each other. Similarly, final backfat (BF) was greatest in CON (P < 0.05), whereas CON and MIN increased final loin depth compared with MM (P < 0.05) with MET not being different. During rearing, 7.7% of all gilts presented lameness, which appeared between 106.8 and 129.7 kg BW confidence interval. Gilts that had been or were lame had reduced BW and average daily gain compared with never lame gilts (P < 0.05). Lameness during rearing was highest (P < 0.01) in gilts fed CON diet (14.8%), with no differences amongst MIN (2.0%), MET (5.3%), or MM (6.5%). In the sow herd, 21% of sows showed lameness and 24% of those were associated with claw lesions. At weaning, gilts fed CON diet had highest (P < 0.01) prevalence of lameness (20.8%) with no differences amongst MIN (6.5%), MET (11.1%), or MM (7.6%). Over the first 2 parities, 27.3% of gilts were culled. On farm, lameness was associated with 0.7 more stillborn piglets (P < 0.10), 1 mm more BF loss in first lactation (P < 0.05), and increased weaning-to-estrus by 3 d (P < 0.05). In conclusion, lameness during rearing was decreased by supplementing organic trace minerals, methionine, and their combination, which also reduced lameness during lactation.

Growth Plate Lesions of Fattening Bulls

Lameness related to growth plate lesions is an important problem in the beef industry. This article describes the macroscopic and microscopic lesions in the distal metatarsal physis of bulls from an association of farmers in northeastern Italy. The metatarsal bones of 62 bulls (12 with severe lameness and 50 without lameness), average age 16.44 ± 1.72 months, were examined at the abattoir. The animals came from the same geographic area and shared intensive husbandry practices and a diet based on maize starch. A total of 124 metatarsal bones were sectioned, and the distal metaphyseal growth plate was grossly examined. Twenty-three cases, including 12 lame and 9 nonlame animals with visible lesions on macroscopic examination, and 2 controls (a total of 46 physes) were examined microscopically. Eight of 12 bulls with severe lameness had a chronic purulent physitis in at least 1 limb. Segmental thickening of the hypertrophic zone, consistent with osteochondrosis (OC), was present contralaterally ( n = 3 cases) and bilaterally ( n = 3 cases) in 6 of these animals. In the group of nonlame bulls, 19 of 50 (38%) had similar segmental thickening of the physis consistent with OC. In the remaining bulls, minor findings included partial closure of the physis and a variable degree of metaphyseal hyperemia. A high incidence of OC was found in both lame and nonlame fattening bulls. It is likely that lame animals were clinically more severe due to secondary hematogenous implantation of bacteria, resulting in a purulent physitis and severe lameness that required emergency slaughter in some cases.

Associations of conformation and locomotive characteristics in growing gilts with osteochondrosis at slaughter

Osteochondrosis (OC) and abnormalities in conformation and locomotive characteristics (CLC) have been associated with premature culling in sows. Several CLC have been suggested to be associated with OC and might help as an in vivo indicator for and increased risk of having OC. The aim of this study was to investigate associations of OC with CLC assessed at several ages in growing gilts from 2 separate experiments over the effects of dietary restriction (Exp. 1) and floor type (Exp. 2) on OC prevalence. In Exp. 1, gilts (n = 211) were subjectively assessed for CLC at, on average, 4, 9, 11, 16, and 24 wk of age. In Exp. 2, gilts (n = 212) were subjectively assessed for CLC at, on average, 4, 9, 11, 16, and 22 wk of age. Assessment was done on 10 conformation and 2 locomotive characteristics using a 9-point grading scale by 2 observers. At, on average, 27 wk of age in Exp. 1 and 24 wk of age in Exp. 2, gilts were slaughtered and the knee, elbow, and hock joints were macroscopically assessed for OC. The CLC most frequently associated with OC were O shape or X shape of the hind legs, straight or bowed hind legs, and straight or sickled hock. X-shaped hind legs were associated with OC at slaughter in the knee joint at 4, 9, and 24 wk of age and at the animal level (all joints taken together) at 4, 9, and 16 wk of age. Straight or bowed hind legs were associated with OC at slaughter in the knee joint at 4 and 11 wk of age; in the hock joint at 11 wk of age; and at the animal level at 4, 9, 11, and 22 wk of age. Straight or sickled hock was associated with OC at slaughter in the knee joint at 4 wk of age, in the hock joint at 9 and 22 wk of age, and at the animal level at 9 and 22 wk of age. Results show that several CLC assessed at several ages were associated with OC, but consistent associations of a type of CLC in every assessment could not be found. The associations of CLC with OC are, therefore, difficult to be used as an in vivo indicator of increased risk for OC.